From 9882dcba636ce45443b0a377efbc87d8a069853d Mon Sep 17 00:00:00 2001
From: Andres Freund <andres@anarazel.de>
Date: Sun, 23 Oct 2022 14:44:43 -0700
Subject: [PATCH v1 10/12] heapam: Add num_pages to RelationGetBufferForTuple()

This will be useful to compute the number of pages to extend a relation by.

Author:
Reviewed-by:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/include/access/hio.h         | 14 +++++++-
 src/backend/access/heap/heapam.c | 60 +++++++++++++++++++++++++++++---
 src/backend/access/heap/hio.c    |  8 ++++-
 3 files changed, 76 insertions(+), 6 deletions(-)

diff --git a/src/include/access/hio.h b/src/include/access/hio.h
index bb90c6fad81..a7326e28d9a 100644
--- a/src/include/access/hio.h
+++ b/src/include/access/hio.h
@@ -30,6 +30,17 @@ typedef struct BulkInsertStateData
 {
 	BufferAccessStrategy strategy;	/* our BULKWRITE strategy object */
 	Buffer		current_buf;	/* current insertion target page */
+
+	/*
+	 * State for bulk extensions. Further pages that were unused at the time
+	 * of the extension. They might be in use by the time we use them though,
+	 * so rechecks are needed.
+	 *
+	 * FIXME: Perhaps these should live in RelationData instead, alongside the
+	 * targetblock?
+	 */
+	BlockNumber	next_free;
+	BlockNumber	last_free;
 } BulkInsertStateData;
 
 
@@ -38,6 +49,7 @@ extern void RelationPutHeapTuple(Relation relation, Buffer buffer,
 extern Buffer RelationGetBufferForTuple(Relation relation, Size len,
 										Buffer otherBuffer, int options,
 										BulkInsertStateData *bistate,
-										Buffer *vmbuffer, Buffer *vmbuffer_other);
+										Buffer *vmbuffer, Buffer *vmbuffer_other,
+										int num_pages);
 
 #endif							/* HIO_H */
diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index bd4d85041d3..51e3a9fff34 100644
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -1977,6 +1977,8 @@ GetBulkInsertState(void)
 	bistate = (BulkInsertState) palloc(sizeof(BulkInsertStateData));
 	bistate->strategy = GetAccessStrategy(BAS_BULKWRITE);
 	bistate->current_buf = InvalidBuffer;
+	bistate->next_free = InvalidBlockNumber;
+	bistate->last_free = InvalidBlockNumber;
 	return bistate;
 }
 
@@ -2050,7 +2052,8 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid,
 	 */
 	buffer = RelationGetBufferForTuple(relation, heaptup->t_len,
 									   InvalidBuffer, options, bistate,
-									   &vmbuffer, NULL);
+									   &vmbuffer, NULL,
+									   0);
 
 	/*
 	 * We're about to do the actual insert -- but check for conflict first, to
@@ -2253,6 +2256,33 @@ heap_prepare_insert(Relation relation, HeapTuple tup, TransactionId xid,
 		return tup;
 }
 
+/*
+ * Helper for heap_multi_insert() that computes the number of full pages s
+ */
+static int
+heap_multi_insert_pages(HeapTuple *heaptuples, int done, int ntuples, Size saveFreeSpace)
+{
+	size_t		page_avail;
+	int			npages = 0;
+
+	page_avail = BLCKSZ - SizeOfPageHeaderData - saveFreeSpace;
+	npages++;
+
+	for (int i = done; i < ntuples; i++)
+	{
+		size_t tup_sz = sizeof(ItemIdData) + MAXALIGN(heaptuples[i]->t_len);
+
+		if (page_avail < tup_sz)
+		{
+			npages++;
+			page_avail = BLCKSZ - SizeOfPageHeaderData - saveFreeSpace;
+		}
+		page_avail -= tup_sz;
+	}
+
+	return npages;
+}
+
 /*
  *	heap_multi_insert	- insert multiple tuples into a heap
  *
@@ -2279,6 +2309,9 @@ heap_multi_insert(Relation relation, TupleTableSlot **slots, int ntuples,
 	Size		saveFreeSpace;
 	bool		need_tuple_data = RelationIsLogicallyLogged(relation);
 	bool		need_cids = RelationIsAccessibleInLogicalDecoding(relation);
+	bool		starting_with_empty_page = false;
+	int			npages = 0;
+	int			npages_used = 0;
 
 	/* currently not needed (thus unsupported) for heap_multi_insert() */
 	AssertArg(!(options & HEAP_INSERT_NO_LOGICAL));
@@ -2329,13 +2362,30 @@ heap_multi_insert(Relation relation, TupleTableSlot **slots, int ntuples,
 	while (ndone < ntuples)
 	{
 		Buffer		buffer;
-		bool		starting_with_empty_page;
 		bool		all_visible_cleared = false;
 		bool		all_frozen_set = false;
 		int			nthispage;
 
 		CHECK_FOR_INTERRUPTS();
 
+		/*
+		 * Compute number of pages needed to insert tuples in the worst
+		 * case. This will be used to determine how much to extend the
+		 * relation by in RelationGetBufferForTuple(), if needed.  If we
+		 * filled a prior page from scratch, we can just update our last
+		 * computation, but if we started with a partially filled page
+		 * recompute from scratch, the number of potentially required pages
+		 * can vary due to tuples needing to fit onto the page, page headers
+		 * etc.
+		 */
+		if (ndone == 0 || !starting_with_empty_page)
+		{
+			npages = heap_multi_insert_pages(heaptuples, ndone, ntuples, saveFreeSpace);
+			npages_used = 0;
+		}
+		else
+			npages_used++;
+
 		/*
 		 * Find buffer where at least the next tuple will fit.  If the page is
 		 * all-visible, this will also pin the requisite visibility map page.
@@ -2345,7 +2395,8 @@ heap_multi_insert(Relation relation, TupleTableSlot **slots, int ntuples,
 		 */
 		buffer = RelationGetBufferForTuple(relation, heaptuples[ndone]->t_len,
 										   InvalidBuffer, options, bistate,
-										   &vmbuffer, NULL);
+										   &vmbuffer, NULL,
+										   npages - npages_used);
 		page = BufferGetPage(buffer);
 
 		starting_with_empty_page = PageGetMaxOffsetNumber(page) == 0;
@@ -3768,7 +3819,8 @@ l2:
 				/* It doesn't fit, must use RelationGetBufferForTuple. */
 				newbuf = RelationGetBufferForTuple(relation, heaptup->t_len,
 												   buffer, 0, NULL,
-												   &vmbuffer_new, &vmbuffer);
+												   &vmbuffer_new, &vmbuffer,
+												   0);
 				/* We're all done. */
 				break;
 			}
diff --git a/src/backend/access/heap/hio.c b/src/backend/access/heap/hio.c
index bc4035a6221..0d43ebb3877 100644
--- a/src/backend/access/heap/hio.c
+++ b/src/backend/access/heap/hio.c
@@ -275,6 +275,11 @@ RelationAddExtraBlocks(Relation relation, BulkInsertState bistate)
  *	Returns pinned and exclusive-locked buffer of a page in given relation
  *	with free space >= given len.
  *
+ *	If num_pages is > 1, the relation will be extended by at least that many
+ *	pages when we decide to extend the relation. This is more efficient for
+ *	callers that know they will need multiple pages
+ *	(e.g. heap_multi_insert()).
+ *
  *	If otherBuffer is not InvalidBuffer, then it references a previously
  *	pinned buffer of another page in the same relation; on return, this
  *	buffer will also be exclusive-locked.  (This case is used by heap_update;
@@ -333,7 +338,8 @@ Buffer
 RelationGetBufferForTuple(Relation relation, Size len,
 						  Buffer otherBuffer, int options,
 						  BulkInsertState bistate,
-						  Buffer *vmbuffer, Buffer *vmbuffer_other)
+						  Buffer *vmbuffer, Buffer *vmbuffer_other,
+						  int num_pages)
 {
 	bool		use_fsm = !(options & HEAP_INSERT_SKIP_FSM);
 	Buffer		buffer = InvalidBuffer;
-- 
2.38.0

